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

    Neuronpedia

    INDEX
    Explanations

    loss and error minimization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PRES
    0.73
     representations
    0.73
     Samaritan
    0.72
     cohorts
    0.72
     shelving
    0.71
     mitophagy
    0.70
    拥有
    0.69
     habits
    0.68
     Rhoda
    0.68
     gateway
    0.67
    POSITIVE LOGITS
     minimization
    0.79
     Minimize
    0.76
     minimize
    0.73
     minimizar
    0.73
     minimizing
    0.73
     Penalty
    0.72
     nyeri
    0.72
     minimising
    0.72
     loss
    0.71
    losses
    0.69
    Act Density 0.364%

    No Known Activations