Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    String

    np_max-act · gemini-2.0-flash

    This neuron activates on Java-style generic type syntax, i.e. angle‐bracket type parameters (e.g. “<String, T>”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    resolver
    -0.06
    scatter
    -0.06
    traits
    -0.06
     ((
    -0.06
    .ModelForm
    -0.06
     ]).
    -0.06
    ('-
    -0.06
     kapsamında
    -0.06
     sisters
    -0.06
    _KERNEL
    -0.06
    POSITIVE LOGITS
    .Sh
    0.08
     een
    0.07
     εί
    0.07
     mô
    0.06
     Runs
    0.06
    .Bind
    0.06
     Орг
    0.06
    vrolet
    0.06
    .В
    0.06
    ’av
    0.06
    Act Density 0.002%

    No Known Activations