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

    Neuronpedia

    INDEX
    Explanations

    Climbing

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect the verb “climb” (in all its forms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dispersion
    -0.08
    128
    -0.07
     nozzle
    -0.07
     net
    -0.07
     福
    -0.06
     rust
    -0.06
     husus
    -0.06
     mode
    -0.06
     technological
    -0.06
     Peng
    -0.06
    POSITIVE LOGITS
     climb
    0.13
     climbing
    0.12
     climbed
    0.12
     climbs
    0.10
     Clim
    0.08
    camp
    0.07
    Interpreter
    0.07
     steep
    0.07
    meg
    0.07
    �
    0.07
    Act Density 0.006%

    No Known Activations